Loading post…
ClickhouseBenchmark
ClickHouse Cloud vs. Snowflake: What drives the real-time performance-per-dollar gap
Summary
The benchmark compares ClickHouse Cloud with Snowflake under a continuous real-time workload, asking whether ingested data becomes query-ready quickly enough for interactive analytics. Both systems received the same 113.2-billion-row NBBO dataset at a target of 1 million rows per second, with matched sorting or clustering keys, pre-aggregations, query schedules, and approximately 16 CPUs of query-serving compute. ClickHouse used native asynchronous inserts and maintained ordering and pre-aggregation during ingestion, while Snowflake used Snowpipe Streaming and Interactive MV refresh as separately metered services. In the end-to-end CostBench comparison, ClickHouse Cloud delivered 412× better performance per dollar: Snowflake’s path cost 3.32× more and its matched queries took 124× longer in total. The comparison attributes the gap to query-readiness work, refresh lag, reconciliation, and growing drill-down latency.
Context
The benchmark examines real-time analytics under continuous ingestion, where incoming data must become query-ready while aggregate and drill-down queries continue running. It focuses on how fresh-data-path work affects both operating cost and query latency.
Approach / What changed
The comparison used the same 113.2-billion-row NBBO dataset, schema, workload, schedule, and paced ingestion target for both systems. ClickHouse used native asynchronous inserts with ordering and pre-aggregation during ingestion; Snowflake used Snowpipe Streaming and Interactive MV refresh. Query-serving compute, layouts, and the complete metered fresh-data path were matched as closely as the platforms allowed.
Takeaways
ClickHouse Cloud delivered 412× better performance per dollar in the end-to-end CostBench comparison.
Snowflake’s end-to-end path cost 3.32× as much as ClickHouse Cloud, while its matched queries took 124× longer in total.
Snowflake’s aggregate paths required reconciliation against lagging materialized views or raw-table scans for current answers; ClickHouse kept raw and pre-aggregated data synchronized during ingestion.
Source and freshness
- Source
- clickhouse.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.